Mercurial > repos > florianbegusch > qiime2_suite
comparison qiime2/qiime_sample-classifier_regress-samples.xml @ 0:370e0b6e9826 draft
Uploaded
author | florianbegusch |
---|---|
date | Wed, 17 Jul 2019 03:05:17 -0400 |
parents | |
children | a025a4a89e07 |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:370e0b6e9826 |
---|---|
1 <?xml version="1.0" ?> | |
2 <tool id="qiime_sample-classifier_regress-samples" name="qiime sample-classifier regress-samples" version="2019.4"> | |
3 <description> - Train and test a cross-validated supervised learning regressor.</description> | |
4 <requirements> | |
5 <requirement type="package" version="2019.4">qiime2</requirement> | |
6 </requirements> | |
7 <command><![CDATA[ | |
8 qiime sample-classifier regress-samples | |
9 | |
10 --i-table=$itable | |
11 --m-metadata-column="$mmetadatacolumn" | |
12 | |
13 #if $ptestsize: | |
14 --p-test-size=$ptestsize | |
15 #end if | |
16 | |
17 #if $pstep: | |
18 --p-step=$pstep | |
19 #end if | |
20 | |
21 #if $pcv: | |
22 --p-cv=$pcv | |
23 #end if | |
24 | |
25 #if str($prandomstate): | |
26 --p-random-state="$prandomstate" | |
27 #end if | |
28 | |
29 #set $pnjobs = '${GALAXY_SLOTS:-4}' | |
30 | |
31 #if str($pnjobs): | |
32 --p-n-jobs="$pnjobs" | |
33 #end if | |
34 | |
35 | |
36 #if $pnestimators: | |
37 --p-n-estimators=$pnestimators | |
38 #end if | |
39 | |
40 #if str($pestimator) != 'None': | |
41 --p-estimator=$pestimator | |
42 #end if | |
43 | |
44 #if $poptimizefeatureselection: | |
45 --p-optimize-feature-selection | |
46 #end if | |
47 | |
48 #if $pstratify: | |
49 --p-stratify | |
50 #end if | |
51 | |
52 #if $pparametertuning: | |
53 --p-parameter-tuning | |
54 #end if | |
55 | |
56 #if str($pmissingsamples) != 'None': | |
57 --p-missing-samples=$pmissingsamples | |
58 #end if | |
59 | |
60 | |
61 #if $input_files_mmetadatafile: | |
62 #def list_dict_to_string(list_dict): | |
63 #set $file_list = list_dict[0]['additional_input'].__getattr__('file_name') | |
64 #for d in list_dict[1:]: | |
65 #set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name') | |
66 #end for | |
67 #return $file_list | |
68 #end def | |
69 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile) | |
70 #end if | |
71 | |
72 | |
73 --o-sample-estimator=osampleestimator | |
74 --o-feature-importance=ofeatureimportance | |
75 --o-predictions=opredictions | |
76 --o-model-summary=omodelsummary | |
77 --o-accuracy-results=oaccuracyresults | |
78 ; | |
79 cp osampleestimator.qza $osampleestimator; | |
80 cp ofeatureimportance.qza $ofeatureimportance; | |
81 cp opredictions.qza $opredictions; | |
82 qiime tools export --input-path omodelsummary.qzv --output-path out && mkdir -p '$omodelsummary.files_path' | |
83 && cp -r out/* '$omodelsummary.files_path' | |
84 && mv '$omodelsummary.files_path/index.html' '$omodelsummary'; | |
85 qiime tools export --input-path oaccuracyresults.qzv --output-path out && mkdir -p '$oaccuracyresults.files_path' | |
86 && cp -r out/* '$oaccuracyresults.files_path' | |
87 && mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults' | |
88 ]]></command> | |
89 <inputs> | |
90 <param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency] Feature table containing all features that should be used for target prediction. [required]" name="itable" optional="False" type="data"/> | |
91 <param label="--m-metadata-column: COLUMN MetadataColumn[Numeric] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text"/> | |
92 <param label="--p-test-size: PROPORTION Range(0.0, 1.0, inclusive_start=False) Fraction of input samples to exclude from training set and use for classifier testing. [default: 0.2]" name="ptestsize" optional="True" type="float" value="0.2"/> | |
93 <param label="--p-step: PROPORTION Range(0.0, 1.0, inclusive_start=False) If optimize-feature-selection is True, step is the percentage of features to remove at each iteration. [default: 0.05]" name="pstep" optional="True" type="float" value="0.05"/> | |
94 <param label="--p-cv: INTEGER Number of k-fold cross-validations to perform. Range(1, None) [default: 5]" name="pcv" optional="True" type="integer" value="5"/> | |
95 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="integer"/> | |
96 <param label="--p-n-estimators: INTEGER Range(1, None) Number of trees to grow for estimation. More trees will improve predictive accuracy up to a threshold level, but will also increase time and memory requirements. This parameter only affects ensemble estimators, such as Random Forest, AdaBoost, ExtraTrees, and GradientBoosting. [default: 100]" name="pnestimators" optional="True" type="integer" value="100" min="1"/> | |
97 <param label="--p-estimator: " name="pestimator" optional="True" type="select"> | |
98 <option selected="True" value="None">Selection is Optional</option> | |
99 <option value="RandomForestRegressor">RandomForestRegressor</option> | |
100 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option> | |
101 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option> | |
102 <option value="AdaBoostRegressor">AdaBoostRegressor</option> | |
103 <option value="ElasticNet">ElasticNet</option> | |
104 <option value="Ridge">Ridge</option> | |
105 <option value="Lasso">Lasso</option> | |
106 <option value="KNeighborsRegressor">KNeighborsRegressor</option> | |
107 <option value="LinearSVR">LinearSVR</option> | |
108 <option value="SVR">SVR</option> | |
109 </param> | |
110 <param label="--p-optimize-feature-selection: --p-no-optimize-feature-selection Automatically optimize input feature selection using recursive feature elimination. [default: False]" name="poptimizefeatureselection" selected="False" type="boolean"/> | |
111 <param label="--p-stratify: --p-no-stratify Evenly stratify training and test data among metadata categories. If True, all values in column must match at least two samples. [default: False]" name="pstratify" selected="False" type="boolean"/> | |
112 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: False]" name="pparametertuning" selected="False" type="boolean"/> | |
113 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select"> | |
114 <option selected="True" value="None">Selection is Optional</option> | |
115 <option value="error">error</option> | |
116 <option value="ignore">ignore</option> | |
117 </param> | |
118 | |
119 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file"> | |
120 <param label="--m-metadata-file: Metadata file or artifact viewable as metadata. This option may be supplied multiple times to merge metadata. [optional]" name="additional_input" type="data" format="tabular,qza,no_unzip.zip" /> | |
121 </repeat> | |
122 | |
123 </inputs> | |
124 <outputs> | |
125 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator"/> | |
126 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/> | |
127 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions"/> | |
128 <data format="html" label="${tool.name} on ${on_string}: modelsummary.qzv" name="omodelsummary"/> | |
129 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.qzv" name="oaccuracyresults"/> | |
130 </outputs> | |
131 <help><![CDATA[ | |
132 Train and test a cross-validated supervised learning regressor. | |
133 ############################################################### | |
134 | |
135 Predicts a continuous sample metadata column using a supervised learning | |
136 regressor. Splits input data into training and test sets. The training set | |
137 is used to train and test the estimator using a stratified k-fold cross- | |
138 validation scheme. This includes optional steps for automated feature | |
139 extraction and hyperparameter optimization. The test set validates | |
140 classification accuracy of the optimized estimator. Outputs classification | |
141 results for test set. For more details on the learning algorithm, see | |
142 http://scikit-learn.org/stable/supervised_learning.html | |
143 | |
144 Parameters | |
145 ---------- | |
146 table : FeatureTable[Frequency] | |
147 Feature table containing all features that should be used for target | |
148 prediction. | |
149 metadata : MetadataColumn[Numeric] | |
150 Numeric metadata column to use as prediction target. | |
151 test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional | |
152 Fraction of input samples to exclude from training set and use for | |
153 classifier testing. | |
154 step : Float % Range(0.0, 1.0, inclusive_start=False), optional | |
155 If optimize_feature_selection is True, step is the percentage of | |
156 features to remove at each iteration. | |
157 cv : Int % Range(1, None), optional | |
158 Number of k-fold cross-validations to perform. | |
159 random_state : Int, optional | |
160 Seed used by random number generator. | |
161 n_estimators : Int % Range(1, None), optional | |
162 Number of trees to grow for estimation. More trees will improve | |
163 predictive accuracy up to a threshold level, but will also increase | |
164 time and memory requirements. This parameter only affects ensemble | |
165 estimators, such as Random Forest, AdaBoost, ExtraTrees, and | |
166 GradientBoosting. | |
167 estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional | |
168 Estimator method to use for sample prediction. | |
169 optimize_feature_selection : Bool, optional | |
170 Automatically optimize input feature selection using recursive feature | |
171 elimination. | |
172 stratify : Bool, optional | |
173 Evenly stratify training and test data among metadata categories. If | |
174 True, all values in column must match at least two samples. | |
175 parameter_tuning : Bool, optional | |
176 Automatically tune hyperparameters using random grid search. | |
177 missing_samples : Str % Choices('error', 'ignore'), optional | |
178 How to handle missing samples in metadata. "error" will fail if missing | |
179 samples are detected. "ignore" will cause the feature table and | |
180 metadata to be filtered, so that only samples found in both files are | |
181 retained. | |
182 | |
183 Returns | |
184 ------- | |
185 sample_estimator : SampleEstimator[Regressor] | |
186 Trained sample estimator. | |
187 feature_importance : FeatureData[Importance] | |
188 Importance of each input feature to model accuracy. | |
189 predictions : SampleData[RegressorPredictions] | |
190 Predicted target values for each input sample. | |
191 model_summary : Visualization | |
192 Summarized parameter and (if enabled) feature selection information for | |
193 the trained estimator. | |
194 accuracy_results : Visualization | |
195 Accuracy results visualization. | |
196 ]]></help> | |
197 <macros> | |
198 <import>qiime_citation.xml</import> | |
199 </macros> | |
200 <expand macro="qiime_citation"/> | |
201 </tool> |